AI 工作流 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
AI 工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AI 工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:cargo install(推荐) cargo install epic-harness # 方式二:从源码编译 git clone https://github.com/epicsagas/epic-harness cd epic-harness cargo build --release # 二进制在 ./target/release/epic-harness
# 查看帮助 epic-harness --help # 基本运行 epic-harness [options] <input> # 详细使用说明请查阅文档 # https://github.com/epicsagas/epic-harness
# epic-harness 配置说明 # 查看配置选项 epic-harness --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export EPIC_HARNESS_CONFIG="/path/to/config.yml"
<blockquote><p align="center">A multi-tool AI agent harness that learns from every session — 22 skills, autonomous pipelines, and a self-evolving engine.</p></blockquote>
<p align="center"><b>One harness, six AI tools. Autonomous from spec to PR. Smarter every session.</b></p>
<p align="center"> <a href="README.md">English</a> | <a href="i18n/ja/README.md">日本語</a> | <a href="i18n/ko/README.md">한국어</a> | <a href="i18n/de/README.md">Deutsch</a> | <a href="i18n/fr/README.md">Français</a> | <a href="i18n/zh-CN/README.md">简体中文</a> | <a href="i18n/zh-TW/README.md">繁體中文</a> | <a href="i18n/pt-BR/README.md">Português</a> | <a href="i18n/es/README.md">Español</a> | <a href="i18n/hi/README.md">हिन्दी</a> </p>
<p align="center"> <a href="https://github.com/epicsagas/epic-harness/stargazers"><img alt="Stars" src="https://img.shields.io/github/stars/epicsagas/epic-harness?style=for-the-badge&labelColor=0d1117&color=ffd700&logo=github&logoColor=white" /></a> <a href="https://github.com/epicsagas/epic-harness/network/members"><img alt="Forks" src="https://img.shields.io/github/forks/epicsagas/epic-harness?style=for-the-badge&labelColor=0d1117&color=2ecc71&logo=github&logoColor=white" /></a> <a href="https://github.com/epicsagas/epic-harness/issues"><img alt="Issues" src="https://img.shields.io/github/issues/epicsagas/epic-harness?style=for-the-badge&labelColor=0d1117&color=ff6b6b&logo=github&logoColor=white" /></a> <a href="https://github.com/epicsagas/epic-harness/commits/main"><img alt="Last commit" src="https://img.shields.io/github/last-commit/epicsagas/epic-harness?style=for-the-badge&labelColor=0d1117&color=58a6ff&logo=git&logoColor=white" /></a> </p> <p align="center"> <a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-Apache--2.0-3fb950?style=for-the-badge&labelColor=0d1117" /></a> <a href="https://github.com/epicsagas/epic-harness/releases"><img alt="Version" src="https://img.shields.io/badge/version-0.4.5-fc8d62?style=for-the-badge&labelColor=0d1117" /></a> <a href="https://blog.rust-lang.org/"><img alt="Rust" src="https://img.shields.io/badge/rust-1.87+-d73a49?style=for-the-badge&labelColor=0d1117&logo=rust&logoColor=white" /></a> <a href="https://github.com/epicsagas/epic-harness#supported-tools"><img alt="Tools" src="https://img.shields.io/badge/tools-6_supported-bc8cff?style=for-the-badge&labelColor=0d1117" /></a> <a href="https://buymeacoffee.com/epicsaga"><img alt="Buy Me a Coffee" src="https://img.shields.io/badge/buy_me_a_coffee-FFDD00?style=for-the-badge&labelColor=0d1117&logo=buymeacoffee&logoColor=black" /></a> </p>
A multi-tool AI agent harness with 22 skills (8 pipeline + 14 quality gates), a self-evolving engine, unified memory, and a single-command autonomous pipeline (/orbit). Works with Claude Code, Codex, Cursor, OpenCode, and Cline — all sharing the same ~/.harness/ data directory. After each session, the evolve loop analyzes failures, generates targeted skills, and loads them next time.
<p align="center"> <img src="./assets/features.png" alt="epic harness features" width="100%" /> </p>
---

First time? Read the Quick Start Guide (5 min). For data storage details, see the Data Map.
After installing the binary, run epic install (or epic install claude) to:
~/.harness/ directory structure~/.harness/config.toml with defaults if absentOn Claude Code, hooks/install.js auto-runs on session start and installs the binary if missing. No manual step needed after the initial clone.
[dashboard] port = 7700 # set to 0 to disable auto-launch auto_open = true # open browser on first session ```
Screens: Dashboard · /orbit Pipeline · Skills (22) · Live Agents · Eval & Evolve · Hooks (6) · Integrations (6) · harness-mem · Settings
---
All tunable parameters in ~/.harness/config.toml. Absent = hardcoded defaults.
```toml
[hook] profile = "standard" # "minimal" | "standard" | "strict" gateguard_hints = true
[scoring] weights = [0.5, 0.3, 0.2] # [success, quality, cost]
[evolution] max_skills = 10 stagnation_limit = 3 improvement_threshold = 0.05 gated_promotion_min = 3
[pattern]
| Command | Purpose |
|---|---|
epic-harness mem recall "HINT" | Smart contextual recall with hint + project + graph neighbors |
epic-harness mem add --title "T" --type TYPE --body "B" | Add node with auto-importance by type (or explicit 0.0–1.0) |
epic-harness mem search "QUERY" | Keyword search (full-text), ranked by importance |
epic-harness mem list | Filter by tag/type/project |
epic-harness mem context | Project-scoped smart recall (no hint) |
epic-harness mem related ID | Graph traversal from a node ID (finds connected knowledge) |
8 skills that orchestrate multi-step workflows. Invoke with /skill-name or let /orbit chain them.
| Skill | What it does |
|---|---|
/orbit | **Full autonomous pipeline**: spec → go → audit → ship → evolve in one shot |
/discover | Problem discovery — 5 Whys, JTBD, Socratic questioning |
/spec | Define requirements — converts to numbered R + AC document |
/go | Build phase — auto-plan → TDD sub-agents → parallel execution → AC verification |
/audit | Audit phase — parallel code review + security audit + tests |
/ship | Shipping phase — isolated test → PR with full audit report → CI watch |
/evolve | Manual evolution trigger — analyze sessions, view dashboard, rollback |
/team | Browse org libraries, hire existing teams, or design new ones |
---
/orbit wraps the entire pipeline into a single autonomous execution. Pick a mode — everything else is hands-off until the PR.
Purple — human steps: mode selection (unclear → interactive), 3× audit failure pause. Green — clear + complex → council auto-spec; clear + simple → direct build; both fully autonomous.
State persisted in $HARNESS_DIR/orbit/PIPELINE-{timestamp}.json — survives context compaction.
Caveats: The agent may bypass the pipeline when modifying orbit itself or editing docs only. See Known Issues (Agent Judgment).
---
<details> <summary>command not found: epic after install</summary>
Add the Cargo bin directory to your PATH:
export PATH="$HOME/.cargo/bin:$PATH"
Add this line to your ~/.zshrc or ~/.bashrc to make it permanent. </details>
<details> <summary>Hooks not firing in Claude Code</summary>
Re-run the install to sync hooks into Claude Code settings:
epic install claude
Then restart Claude Code. Hooks are written to ~/.claude/settings.json. </details>
<details> <summary>Permission denied on macOS (Gatekeeper)</summary>
macOS may block unsigned binaries downloaded from the internet:
xattr -d com.apple.quarantine ~/.cargo/bin/epic-harness
xattr -d com.apple.quarantine ~/.cargo/bin/epic </details>
<details> <summary>epic: binary not found inside plugin hooks</summary>
The plugin looks for the binary in hooks/bin/epic-harness first. After updating via cargo install, copy it:
cp ~/.cargo/bin/epic-harness hooks/bin/epic-harness </details>
---
高质量的AI工作流项目,具有自我进化能力
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,AI 工作流 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | epic-harness |
| 原始描述 | 开源AI工作流:Multi-tool AI agent harness — 22 skills, self-evolving engine, unified memory, a。⭐7 · Rust |
| Topics | ai-agentclaudeclideveloper-toolsrust |
| GitHub | https://github.com/epicsagas/epic-harness |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-06-07 · 更新时间:2026-06-08 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端